{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:N3YEHX4ODV3N4ITAC6ZPIBYWM7","short_pith_number":"pith:N3YEHX4O","schema_version":"1.0","canonical_sha256":"6ef043df8e1d76de226017b2f4071667dda9b2e51949987c77b47ec3195e9549","source":{"kind":"arxiv","id":"1910.13496","version":2},"attestation_state":"computed","paper":{"title":"Asymptotically unbiased estimation of physical observables with neural samplers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cond-mat.stat-mech","authors_text":"Kim A. Nicoli, Klaus-Robert M\\\"uller, Nils Strodthoff, Pan Kessel, Shinichi Nakajima, Wojciech Samek","submitted_at":"2019-10-29T19:40:08Z","abstract_excerpt":"We propose a general framework for the estimation of observables with generative neural samplers focusing on modern deep generative neural networks that provide an exact sampling probability. In this framework, we present asymptotically unbiased estimators for generic observables, including those that explicitly depend on the partition function such as free energy or entropy, and derive corresponding variance estimators. We demonstrate their practical applicability by numerical experiments for the 2d Ising model which highlight the superiority over existing methods. Our approach greatly enhanc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1910.13496","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.stat-mech","submitted_at":"2019-10-29T19:40:08Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"48791b32b7d66342eade42d54b40dc814bdd2e8805285e2bb893972b95cc5332","abstract_canon_sha256":"d4a81c03ac85c350a20ce8857733ae0be1f2dc22b5151b83a07f064a3449207a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:04:04.474266Z","signature_b64":"ayfBXS7E9MTd8d8B4LWNMHuvq1HikENfbAfJZRMeTTld1/JKwXuTkz7A5Hcz29ebzjHQev8g1G/InlwtsImODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ef043df8e1d76de226017b2f4071667dda9b2e51949987c77b47ec3195e9549","last_reissued_at":"2026-07-05T02:04:04.473866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:04:04.473866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asymptotically unbiased estimation of physical observables with neural samplers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cond-mat.stat-mech","authors_text":"Kim A. Nicoli, Klaus-Robert M\\\"uller, Nils Strodthoff, Pan Kessel, Shinichi Nakajima, Wojciech Samek","submitted_at":"2019-10-29T19:40:08Z","abstract_excerpt":"We propose a general framework for the estimation of observables with generative neural samplers focusing on modern deep generative neural networks that provide an exact sampling probability. In this framework, we present asymptotically unbiased estimators for generic observables, including those that explicitly depend on the partition function such as free energy or entropy, and derive corresponding variance estimators. We demonstrate their practical applicability by numerical experiments for the 2d Ising model which highlight the superiority over existing methods. Our approach greatly enhanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.13496","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.13496/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1910.13496","created_at":"2026-07-05T02:04:04.473917+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.13496v2","created_at":"2026-07-05T02:04:04.473917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.13496","created_at":"2026-07-05T02:04:04.473917+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3YEHX4ODV3N","created_at":"2026-07-05T02:04:04.473917+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3YEHX4ODV3N4ITA","created_at":"2026-07-05T02:04:04.473917+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3YEHX4O","created_at":"2026-07-05T02:04:04.473917+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.25704","citing_title":"Scaling flow-based approaches for topology sampling in $\\mathrm{SU}(3)$ gauge theory","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27738","citing_title":"Sampling two-dimensional spin systems with transformers","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N3YEHX4ODV3N4ITAC6ZPIBYWM7","json":"https://pith.science/pith/N3YEHX4ODV3N4ITAC6ZPIBYWM7.json","graph_json":"https://pith.science/api/pith-number/N3YEHX4ODV3N4ITAC6ZPIBYWM7/graph.json","events_json":"https://pith.science/api/pith-number/N3YEHX4ODV3N4ITAC6ZPIBYWM7/events.json","paper":"https://pith.science/paper/N3YEHX4O"},"agent_actions":{"view_html":"https://pith.science/pith/N3YEHX4ODV3N4ITAC6ZPIBYWM7","download_json":"https://pith.science/pith/N3YEHX4ODV3N4ITAC6ZPIBYWM7.json","view_paper":"https://pith.science/paper/N3YEHX4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.13496&json=true","fetch_graph":"https://pith.science/api/pith-number/N3YEHX4ODV3N4ITAC6ZPIBYWM7/graph.json","fetch_events":"https://pith.science/api/pith-number/N3YEHX4ODV3N4ITAC6ZPIBYWM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3YEHX4ODV3N4ITAC6ZPIBYWM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3YEHX4ODV3N4ITAC6ZPIBYWM7/action/storage_attestation","attest_author":"https://pith.science/pith/N3YEHX4ODV3N4ITAC6ZPIBYWM7/action/author_attestation","sign_citation":"https://pith.science/pith/N3YEHX4ODV3N4ITAC6ZPIBYWM7/action/citation_signature","submit_replication":"https://pith.science/pith/N3YEHX4ODV3N4ITAC6ZPIBYWM7/action/replication_record"}},"created_at":"2026-07-05T02:04:04.473917+00:00","updated_at":"2026-07-05T02:04:04.473917+00:00"}